8 papers
Preconditioned Inexact Stochastic ADMM for Deep Model
Shenglong Zhou, Ouya Wang, Ziyan Luo +2
Deep learning models are usually trained with stochastic gradient descent-based algorithms, but these optimizers face inherent limitations, such as slow convergence and stringent a…
Compositional Behavioral Semantics for State Abstraction in Reinforcement Learning
Yivan Zhang, Ziyan Luo, Manuel Baltieri
State abstraction plays a key role in scaling reinforcement learning to complex but structured systems. In studying such systems, a wide range of behavioral structures have been st…
Sharp-Peak Functions for Exactly Penalizing Binary Integer Programming
Shenglong Zhou, Shuai Li, Hui Zhang +1
Unconstrained binary integer programming (UBIP) is a challenging optimization problem due to the presence of binary variables. To address the challenge, we introduce a novel class…
Low Rank Support Quaternion Matrix Machine
Wang Chen, Ziyan Luo, Shuangyue Wang
Input features are conventionally represented as vectors, matrices, or third order tensors in the real field, for color image classification. Inspired by the success of quaternion…
Sparse Quadratically Constrained Quadratic Programming via Semismooth Newton Method
Shuai Li, Shenglong Zhou, Ziyan Luo
Quadratically constrained quadratic programming (QCQP) has long been recognized as a computationally challenging problem, particularly in large-scale or high-dimensional settings w…
Understanding Behavioral Metric Learning: A Large-Scale Study on Distracting Reinforcement Learning Environments
Ziyan Luo, Tianwei Ni, Pierre-Luc Bacon +2
A key approach to state abstraction is approximating behavioral metrics (notably, bisimulation metrics) in the observation space and embedding these learned distances in the repres…